© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13848
    Prev
    Next
    INDEX
    Explanations

    modelmodel numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on alphanumeric product model identifiers (strings of uppercase letters/digits like “DF-U5412H” or “MDF-S3304U337D”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    II
    0.96
     II
    0.95
     III
    0.89
    2
    0.89
    /
    0.89
    -
    0.88
    III
    0.82
    1
    0.81
    4
    0.78
    6
    0.78
    POSITIVE LOGITS
    㵴
    0.71
    客厅
    0.70
     habitantes
    0.68
    起き
    0.68
    㩴
    0.68
    राधना
    0.68
     Adapun
    0.66
     Alemania
    0.66
     prijatel
    0.66
     금액
    0.65
    Activations Density 0.008%

    No Known Activations